File size: 2,358 Bytes
6d52f6f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
from transformers import PretrainedConfig
from typing import List
class LMConfig(PretrainedConfig):
model_type = "minimind"
def __init__(
self,
dim: int = 512,
n_layers: int = 8,
n_heads: int = 16,
n_kv_heads: int = 8,
vocab_size: int = 6400,
hidden_dim: int = None,
multiple_of: int = 64,
norm_eps: float = 1e-5,
max_seq_len: int = 512,
dropout: float = 0.0,
flash_attn: bool = True,
####################################################
# Here are the specific configurations of MOE
# When use_moe is false, the following is invalid
####################################################
use_moe: bool = True,
num_experts_per_tok=2,
n_routed_experts=4,
n_shared_experts: bool = True,
scoring_func='softmax',
aux_loss_alpha=0.01,
seq_aux=True,
norm_topk_prob=True,
**kwargs,
):
self.dim = dim
self.n_layers = n_layers
self.n_heads = n_heads
self.n_kv_heads = n_kv_heads
self.vocab_size = vocab_size
self.hidden_dim = hidden_dim
self.multiple_of = multiple_of
self.norm_eps = norm_eps
self.max_seq_len = max_seq_len
self.dropout = dropout
self.flash_attn = flash_attn
####################################################
# Here are the specific configurations of MOE
# When use_moe is false, the following is invalid
####################################################
self.use_moe = use_moe
self.num_experts_per_tok = num_experts_per_tok # 每个token选择的专家数量
self.n_routed_experts = n_routed_experts # 总的专家数量
self.n_shared_experts = n_shared_experts # 共享专家
self.scoring_func = scoring_func # 评分函数，默认为'softmax'
self.aux_loss_alpha = aux_loss_alpha # 辅助损失的alpha参数
self.seq_aux = seq_aux # 是否在序列级别上计算辅助损失
self.norm_topk_prob = norm_topk_prob # 是否标准化top-k概率
super().__init__(**kwargs)
|